R Week 08 Assignment
Kamilly Lombert
2/29/2025
Explanation of the template
Hi, my name is Kamilly, but I also go by “Kami”. I am a rising senior majoring in environmental studies. One interesting fact about me is that i have a pet cat and a pet bird. I am interested in plants and nature and i enjoy going to the park.
R Spatial Lab Assignment # 1
Task 1:Join the COVID-19 data to the NYC zip code area data
covid_data<- read.csv("R-Spatial_II_Lab/R-Spatial_II_Lab/tests-by-zcta_2021_04_23.csv")
covid_sf<- st_as_sf(covid_data, coords=c("lon","lat"), crs=4326)
nyc_zipcode<-st_read("R-Spatial_I_Lab/ZIP_CODE_040114/ZIP_CODE_040114.shp")## Reading layer `ZIP_CODE_040114' from data source
## `C:\Users\Kami\Downloads\Section_08\R-Spatial_I_Lab\ZIP_CODE_040114\ZIP_CODE_040114.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 263 features and 12 fields
## Geometry type: POLYGON
## Dimension: XY
## Bounding box: xmin: 913129 ymin: 120020.9 xmax: 1067494 ymax: 272710.9
## Projected CRS: NAD83 / New York Long Island (ftUS)zipcode_sf<-st_transform(nyc_zipcode,4326)
zipcode_merge<- st_join(zipcode_sf,covid_sf)
head(zipcode_merge)## Simple feature collection with 6 features and 23 fields
## Geometry type: POLYGON
## Dimension: XY
## Bounding box: xmin: -73.99193 ymin: 40.63029 xmax: -73.78805 ymax: 40.6863
## Geodetic CRS: WGS 84
## ZIPCODE BLDGZIP PO_NAME POPULATION AREA STATE COUNTY ST_FIPS CTY_FIPS
## 1 11436 0 Jamaica 18681 22699295 NY Queens 36 081
## 2 11213 0 Brooklyn 62426 29631004 NY Kings 36 047
## 3 11212 0 Brooklyn 83866 41972104 NY Kings 36 047
## 4 11225 0 Brooklyn 56527 23698630 NY Kings 36 047
## 5 11218 0 Brooklyn 72280 36868799 NY Kings 36 047
## 6 11226 0 Brooklyn 106132 39408598 NY Kings 36 047
## URL SHAPE_AREA SHAPE_LEN MODIFIED_ZCTA
## 1 http://www.usps.com/ 0 0 11436
## 2 http://www.usps.com/ 0 0 11213
## 3 http://www.usps.com/ 0 0 11212
## 4 http://www.usps.com/ 0 0 11225
## 5 http://www.usps.com/ 0 0 11218
## 6 http://www.usps.com/ 0 0 11226
## NEIGHBORHOOD_NAME BOROUGH_GROUP label
## 1 South Jamaica/South Ozone Park Queens 11436
## 2 Crown Heights (East) Brooklyn 11213
## 3 Ocean Hill-Brownsville Brooklyn 11212
## 4 Crown Heights (West)/Prospect Lefferts Gardens Brooklyn 11225
## 5 Kensington/Windsor Terrace Brooklyn 11218
## 6 Flatbush/Prospect Lefferts Gardens Brooklyn 11226
## COVID_CASE_COUNT COVID_CASE_RATE POP_DENOMINATOR COVID_DEATH_COUNT
## 1 1888 9419.96 20042.54 64
## 2 5166 7996.75 64601.26 203
## 3 7182 9709.74 73966.99 330
## 4 3833 6664.50 57513.69 177
## 5 6199 8377.49 73995.92 218
## 6 7279 7476.75 97355.08 368
## COVID_DEATH_RATE PERCENT_POSITIVE TOTAL_COVID_TESTS
## 1 319.32 17.57 11082
## 2 314.24 13.72 38560
## 3 446.14 15.64 47319
## 4 307.75 11.62 33709
## 5 294.61 13.93 45884
## 6 378.00 13.33 56287
## geometry
## 1 POLYGON ((-73.80585 40.6829...
## 2 POLYGON ((-73.9374 40.67973...
## 3 POLYGON ((-73.90294 40.6708...
## 4 POLYGON ((-73.95797 40.6706...
## 5 POLYGON ((-73.97208 40.6506...
## 6 POLYGON ((-73.9619 40.65487...plot(zipcode_merge["COVID_CASE_COUNT"])
Task 2:
nyc_foods<-st_read("R-Spatial_II_Lab/R-Spatial_II_Lab/nycFoodStore.shp")## Reading layer `nycFoodStore' from data source
## `C:\Users\Kami\Downloads\Section_08\R-Spatial_II_Lab\R-Spatial_II_Lab\nycFoodStore.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 11300 features and 16 fields
## Geometry type: POINT
## Dimension: XY
## Bounding box: xmin: -74.2484 ymin: 40.50782 xmax: -73.67061 ymax: 40.91008
## Geodetic CRS: WGS 84zipcode_foods<-zipcode_merge %>%
st_join(nyc_foods) %>%
group_by(geometry)%>%
mutate(n_food_stores=n())
plot(zipcode_foods["n_food_stores"])
Task 3:
nychealth<-read_csv("R-Spatial_I_Lab/NYS_Health_Facility.csv")## Rows: 3985 Columns: 36
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (27): Facility Name, Short Description, Description, Facility Open Date,...
## dbl (9): Facility ID, Facility Phone Number, Facility Fax Number, Facility ...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.missing_long <- is.na(nychealth$`Facility Longitude`)
missing_lat <- is.na(nychealth$`Facility Latitude`)
missing_coords <- missing_long | missing_lat
nychealth_clean <- nychealth[!missing_coords, ]
nychealthsf <- st_as_sf(nychealth_clean, coords = c("Facility Longitude", "Facility Latitude"), crs = 4326)
zipcode_health<-zipcode_foods %>%
st_join(nychealthsf) %>%
group_by(geometry)%>%
mutate(n_health_fac=n())
zipcode_health<-zipcode_health %>%
filter(Description == "Hospital") %>%
group_by(geometry)%>%
mutate(n_hospital_fac=n())
zipcode_health <- zipcode_health %>%
rename("Number of Hospitals" = "n_hospital_fac")
plot(zipcode_health["Number of Hospitals"])
Task 4:
census_tract<-st_read("R-Spatial_II_Lab/R-Spatial_II_Lab/2010 Census Tracts/geo_export_1dc7b645-647b-4806-b9a0-7b79660f120a.shp")## Reading layer `geo_export_1dc7b645-647b-4806-b9a0-7b79660f120a' from data source `C:\Users\Kami\Downloads\Section_08\R-Spatial_II_Lab\R-Spatial_II_Lab\2010 Census Tracts\geo_export_1dc7b645-647b-4806-b9a0-7b79660f120a.shp'
## using driver `ESRI Shapefile'
## Simple feature collection with 2165 features and 11 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: -74.25559 ymin: 40.49612 xmax: -73.70001 ymax: 40.91553
## Geodetic CRS: WGS84(DD)ACS_data<-read_csv("R-Spatial_II_Lab/R-Spatial_II_Lab/ACSDP5Y2018.DP05_data_with_overlays_2020-04-22T132935.csv")## Rows: 2167 Columns: 358
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (181): GEO_ID, NAME, DP05_0031PM, DP05_0032E, DP05_0032M, DP05_0032PE, D...
## dbl (177): Totalpop, DP05_0033M, DP05_0033PE, DP05_0034E, DP05_0034M, DP05_0...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.c_tract<-census_tract %<>% dplyr::mutate(cntyFIPS = case_when(
boro_name == 'Bronx' ~ '005',
boro_name == 'Brooklyn' ~ '047',
boro_name == 'Manhattan' ~ '061',
boro_name == 'Queens' ~ '081',
boro_name == 'Staten Island' ~ '085'),
tractFIPS = paste(cntyFIPS, ct2010, sep='')
)
acsData <- ACS_data %>%
dplyr::select(GEO_ID,
totPop = DP05_0001E,
elderlyPop = DP05_0024E, # >= 65
malePop = DP05_0002E,
femalePop = DP05_0003E,
whitePop = DP05_0037E,
blackPop = DP05_0038E,
asianPop = DP05_0067E,
hispanicPop = DP05_0071E,
adultPop = DP05_0021E,
citizenAdult = DP05_0087E) %>%
mutate(censusCode = str_sub(GEO_ID, -9, -1))
acsData %>%
magrittr::extract(1:10,)## # A tibble: 10 × 12
## GEO_ID totPop elderlyPop malePop femalePop whitePop blackPop asianPop
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1400000US3600… 7080 51 6503 577 1773 4239 130
## 2 1400000US3600… 4542 950 2264 2278 2165 1279 119
## 3 1400000US3600… 5634 710 2807 2827 2623 1699 226
## 4 1400000US3600… 5917 989 2365 3552 2406 2434 68
## 5 1400000US3600… 2765 76 1363 1402 585 1041 130
## 6 1400000US3600… 9409 977 4119 5290 3185 4487 29
## 7 1400000US3600… 4600 648 2175 2425 479 2122 27
## 8 1400000US3600… 172 0 121 51 69 89 14
## 9 1400000US3600… 5887 548 2958 2929 903 1344 68
## 10 1400000US3600… 2868 243 1259 1609 243 987 0
## # ℹ 4 more variables: hispanicPop <dbl>, adultPop <dbl>, citizenAdult <dbl>,
## # censusCode <chr>popData <- merge(c_tract, acsData, by.x ='tractFIPS', by.y = 'censusCode')
plot(popData["blackPop"])
Task 5:
popData5<-st_transform(popData, 4326)
ACS_zip <- zipcode_sf %>%
st_join(popData5) %>%
group_by(ZIPCODE)
plot(ACS_zip["totPop"]) 